linux_dsm_epyc7002/kernel/power/swap.c

634 lines
14 KiB
C
Raw Normal View History

/*
* linux/kernel/power/swap.c
*
* This file provides functions for reading the suspend image from
* and writing it to a swap partition.
*
* Copyright (C) 1998,2001-2005 Pavel Machek <pavel@suse.cz>
* Copyright (C) 2006 Rafael J. Wysocki <rjw@sisk.pl>
*
* This file is released under the GPLv2.
*
*/
#include <linux/module.h>
#include <linux/smp_lock.h>
#include <linux/file.h>
#include <linux/utsname.h>
#include <linux/version.h>
#include <linux/delay.h>
#include <linux/bitops.h>
#include <linux/genhd.h>
#include <linux/device.h>
#include <linux/buffer_head.h>
#include <linux/bio.h>
#include <linux/blkdev.h>
#include <linux/swap.h>
#include <linux/swapops.h>
#include <linux/pm.h>
#include "power.h"
extern char resume_file[];
#define SWSUSP_SIG "S1SUSPEND"
static struct swsusp_header {
char reserved[PAGE_SIZE - 20 - sizeof(sector_t)];
sector_t image;
char orig_sig[10];
char sig[10];
} __attribute__((packed, aligned(PAGE_SIZE))) swsusp_header;
/*
* General things
*/
static unsigned short root_swap = 0xffff;
static struct block_device *resume_bdev;
/**
* submit - submit BIO request.
* @rw: READ or WRITE.
* @off physical offset of page.
* @page: page we're reading or writing.
* @bio_chain: list of pending biod (for async reading)
*
* Straight from the textbook - allocate and initialize the bio.
* If we're reading, make sure the page is marked as dirty.
* Then submit it and, if @bio_chain == NULL, wait.
*/
static int submit(int rw, pgoff_t page_off, struct page *page,
struct bio **bio_chain)
{
struct bio *bio;
bio = bio_alloc(__GFP_WAIT | __GFP_HIGH, 1);
if (!bio)
return -ENOMEM;
bio->bi_sector = page_off * (PAGE_SIZE >> 9);
bio->bi_bdev = resume_bdev;
bio->bi_end_io = end_swap_bio_read;
if (bio_add_page(bio, page, PAGE_SIZE, 0) < PAGE_SIZE) {
printk("swsusp: ERROR: adding page to bio at %ld\n", page_off);
bio_put(bio);
return -EFAULT;
}
lock_page(page);
bio_get(bio);
if (bio_chain == NULL) {
submit_bio(rw | (1 << BIO_RW_SYNC), bio);
wait_on_page_locked(page);
if (rw == READ)
bio_set_pages_dirty(bio);
bio_put(bio);
} else {
if (rw == READ)
get_page(page); /* These pages are freed later */
bio->bi_private = *bio_chain;
*bio_chain = bio;
submit_bio(rw | (1 << BIO_RW_SYNC), bio);
}
return 0;
}
static int bio_read_page(pgoff_t page_off, void *addr, struct bio **bio_chain)
{
return submit(READ, page_off, virt_to_page(addr), bio_chain);
}
static int bio_write_page(pgoff_t page_off, void *addr, struct bio **bio_chain)
{
return submit(WRITE, page_off, virt_to_page(addr), bio_chain);
}
static int wait_on_bio_chain(struct bio **bio_chain)
{
struct bio *bio;
struct bio *next_bio;
int ret = 0;
if (bio_chain == NULL)
return 0;
bio = *bio_chain;
if (bio == NULL)
return 0;
while (bio) {
struct page *page;
next_bio = bio->bi_private;
page = bio->bi_io_vec[0].bv_page;
wait_on_page_locked(page);
if (!PageUptodate(page) || PageError(page))
ret = -EIO;
put_page(page);
bio_put(bio);
bio = next_bio;
}
*bio_chain = NULL;
return ret;
}
/*
* Saving part
*/
static int mark_swapfiles(sector_t start)
{
int error;
bio_read_page(swsusp_resume_block, &swsusp_header, NULL);
if (!memcmp("SWAP-SPACE",swsusp_header.sig, 10) ||
!memcmp("SWAPSPACE2",swsusp_header.sig, 10)) {
memcpy(swsusp_header.orig_sig,swsusp_header.sig, 10);
memcpy(swsusp_header.sig,SWSUSP_SIG, 10);
swsusp_header.image = start;
error = bio_write_page(swsusp_resume_block,
&swsusp_header, NULL);
} else {
printk(KERN_ERR "swsusp: Swap header not found!\n");
error = -ENODEV;
}
return error;
}
/**
* swsusp_swap_check - check if the resume device is a swap device
* and get its index (if so)
*/
static int swsusp_swap_check(void) /* This is called before saving image */
{
int res;
res = swap_type_of(swsusp_resume_device, swsusp_resume_block);
if (res < 0)
return res;
root_swap = res;
resume_bdev = open_by_devnum(swsusp_resume_device, FMODE_WRITE);
if (IS_ERR(resume_bdev))
return PTR_ERR(resume_bdev);
res = set_blocksize(resume_bdev, PAGE_SIZE);
if (res < 0)
blkdev_put(resume_bdev);
return res;
}
/**
* write_page - Write one page to given swap location.
* @buf: Address we're writing.
* @offset: Offset of the swap page we're writing to.
* @bio_chain: Link the next write BIO here
*/
static int write_page(void *buf, sector_t offset, struct bio **bio_chain)
{
void *src;
if (!offset)
return -ENOSPC;
if (bio_chain) {
src = (void *)__get_free_page(__GFP_WAIT | __GFP_HIGH);
if (src) {
memcpy(src, buf, PAGE_SIZE);
} else {
WARN_ON_ONCE(1);
bio_chain = NULL; /* Go synchronous */
src = buf;
}
} else {
src = buf;
}
return bio_write_page(offset, src, bio_chain);
}
/*
* The swap map is a data structure used for keeping track of each page
* written to a swap partition. It consists of many swap_map_page
* structures that contain each an array of MAP_PAGE_SIZE swap entries.
* These structures are stored on the swap and linked together with the
* help of the .next_swap member.
*
* The swap map is created during suspend. The swap map pages are
* allocated and populated one at a time, so we only need one memory
* page to set up the entire structure.
*
* During resume we also only need to use one swap_map_page structure
* at a time.
*/
#define MAP_PAGE_ENTRIES (PAGE_SIZE / sizeof(sector_t) - 1)
struct swap_map_page {
sector_t entries[MAP_PAGE_ENTRIES];
sector_t next_swap;
};
/**
* The swap_map_handle structure is used for handling swap in
* a file-alike way
*/
struct swap_map_handle {
struct swap_map_page *cur;
sector_t cur_swap;
struct bitmap_page *bitmap;
unsigned int k;
};
static void release_swap_writer(struct swap_map_handle *handle)
{
if (handle->cur)
free_page((unsigned long)handle->cur);
handle->cur = NULL;
if (handle->bitmap)
free_bitmap(handle->bitmap);
handle->bitmap = NULL;
}
static int get_swap_writer(struct swap_map_handle *handle)
{
handle->cur = (struct swap_map_page *)get_zeroed_page(GFP_KERNEL);
if (!handle->cur)
return -ENOMEM;
handle->bitmap = alloc_bitmap(count_swap_pages(root_swap, 0));
if (!handle->bitmap) {
release_swap_writer(handle);
return -ENOMEM;
}
handle->cur_swap = alloc_swapdev_block(root_swap, handle->bitmap);
if (!handle->cur_swap) {
release_swap_writer(handle);
return -ENOSPC;
}
handle->k = 0;
return 0;
}
static int swap_write_page(struct swap_map_handle *handle, void *buf,
struct bio **bio_chain)
{
int error = 0;
sector_t offset;
if (!handle->cur)
return -EINVAL;
offset = alloc_swapdev_block(root_swap, handle->bitmap);
error = write_page(buf, offset, bio_chain);
if (error)
return error;
handle->cur->entries[handle->k++] = offset;
if (handle->k >= MAP_PAGE_ENTRIES) {
error = wait_on_bio_chain(bio_chain);
if (error)
goto out;
offset = alloc_swapdev_block(root_swap, handle->bitmap);
if (!offset)
return -ENOSPC;
handle->cur->next_swap = offset;
error = write_page(handle->cur, handle->cur_swap, NULL);
if (error)
goto out;
memset(handle->cur, 0, PAGE_SIZE);
handle->cur_swap = offset;
handle->k = 0;
}
out:
return error;
}
static int flush_swap_writer(struct swap_map_handle *handle)
{
if (handle->cur && handle->cur_swap)
return write_page(handle->cur, handle->cur_swap, NULL);
else
return -EINVAL;
}
/**
* save_image - save the suspend image data
*/
static int save_image(struct swap_map_handle *handle,
struct snapshot_handle *snapshot,
unsigned int nr_to_write)
{
unsigned int m;
int ret;
int error = 0;
int nr_pages;
int err2;
struct bio *bio;
struct timeval start;
struct timeval stop;
printk("Saving image data pages (%u pages) ... ", nr_to_write);
m = nr_to_write / 100;
if (!m)
m = 1;
nr_pages = 0;
bio = NULL;
do_gettimeofday(&start);
do {
ret = snapshot_read_next(snapshot, PAGE_SIZE);
if (ret > 0) {
error = swap_write_page(handle, data_of(*snapshot),
&bio);
if (error)
break;
if (!(nr_pages % m))
printk("\b\b\b\b%3d%%", nr_pages / m);
nr_pages++;
}
} while (ret > 0);
err2 = wait_on_bio_chain(&bio);
do_gettimeofday(&stop);
if (!error)
error = err2;
if (!error)
printk("\b\b\b\bdone\n");
swsusp_show_speed(&start, &stop, nr_to_write, "Wrote");
return error;
}
/**
* enough_swap - Make sure we have enough swap to save the image.
*
* Returns TRUE or FALSE after checking the total amount of swap
* space avaiable from the resume partition.
*/
static int enough_swap(unsigned int nr_pages)
{
unsigned int free_swap = count_swap_pages(root_swap, 1);
pr_debug("swsusp: free swap pages: %u\n", free_swap);
[PATCH] swsusp: Use memory bitmaps during resume Make swsusp use memory bitmaps to store its internal information during the resume phase of the suspend-resume cycle. If the pfns of saveable pages are saved during the suspend phase instead of the kernel virtual addresses of these pages, we can use them during the resume phase directly to set the corresponding bits in a memory bitmap. Then, this bitmap is used to mark the page frames corresponding to the pages that were saveable before the suspend (aka "unsafe" page frames). Next, we allocate as many page frames as needed to store the entire suspend image and make sure that there will be some extra free "safe" page frames for the list of PBEs constructed later. Subsequently, the image is loaded and, if possible, the data loaded from it are written into their "original" page frames (ie. the ones they had occupied before the suspend). The image data that cannot be written into their "original" page frames are loaded into "safe" page frames and their "original" kernel virtual addresses, as well as the addresses of the "safe" pages containing their copies, are stored in a list of PBEs. Finally, the list of PBEs is used to copy the remaining image data into their "original" page frames (this is done atomically, by the architecture-dependent parts of swsusp). Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl> Acked-by: Pavel Machek <pavel@ucw.cz> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-09-26 13:32:55 +07:00
return free_swap > nr_pages + PAGES_FOR_IO;
}
/**
* swsusp_write - Write entire image and metadata.
*
* It is important _NOT_ to umount filesystems at this point. We want
* them synced (in case something goes wrong) but we DO not want to mark
* filesystem clean: it is not. (And it does not matter, if we resume
* correctly, we'll mark system clean, anyway.)
*/
int swsusp_write(void)
{
struct swap_map_handle handle;
struct snapshot_handle snapshot;
struct swsusp_info *header;
int error;
error = swsusp_swap_check();
if (error) {
printk(KERN_ERR "swsusp: Cannot find swap device, try "
"swapon -a.\n");
return error;
}
memset(&snapshot, 0, sizeof(struct snapshot_handle));
error = snapshot_read_next(&snapshot, PAGE_SIZE);
if (error < PAGE_SIZE) {
if (error >= 0)
error = -EFAULT;
goto out;
}
header = (struct swsusp_info *)data_of(snapshot);
if (!enough_swap(header->pages)) {
printk(KERN_ERR "swsusp: Not enough free swap\n");
error = -ENOSPC;
goto out;
}
error = get_swap_writer(&handle);
if (!error) {
sector_t start = handle.cur_swap;
error = swap_write_page(&handle, header, NULL);
if (!error)
error = save_image(&handle, &snapshot,
header->pages - 1);
if (!error) {
flush_swap_writer(&handle);
printk("S");
error = mark_swapfiles(start);
printk("|\n");
}
}
if (error)
free_all_swap_pages(root_swap, handle.bitmap);
release_swap_writer(&handle);
out:
swsusp_close();
return error;
}
/**
* The following functions allow us to read data using a swap map
* in a file-alike way
*/
static void release_swap_reader(struct swap_map_handle *handle)
{
if (handle->cur)
free_page((unsigned long)handle->cur);
handle->cur = NULL;
}
static int get_swap_reader(struct swap_map_handle *handle, sector_t start)
{
int error;
if (!start)
return -EINVAL;
handle->cur = (struct swap_map_page *)get_zeroed_page(__GFP_WAIT | __GFP_HIGH);
if (!handle->cur)
return -ENOMEM;
error = bio_read_page(start, handle->cur, NULL);
if (error) {
release_swap_reader(handle);
return error;
}
handle->k = 0;
return 0;
}
static int swap_read_page(struct swap_map_handle *handle, void *buf,
struct bio **bio_chain)
{
sector_t offset;
int error;
if (!handle->cur)
return -EINVAL;
offset = handle->cur->entries[handle->k];
if (!offset)
return -EFAULT;
error = bio_read_page(offset, buf, bio_chain);
if (error)
return error;
if (++handle->k >= MAP_PAGE_ENTRIES) {
error = wait_on_bio_chain(bio_chain);
handle->k = 0;
offset = handle->cur->next_swap;
if (!offset)
release_swap_reader(handle);
else if (!error)
error = bio_read_page(offset, handle->cur, NULL);
}
return error;
}
/**
* load_image - load the image using the swap map handle
* @handle and the snapshot handle @snapshot
* (assume there are @nr_pages pages to load)
*/
static int load_image(struct swap_map_handle *handle,
struct snapshot_handle *snapshot,
unsigned int nr_to_read)
{
unsigned int m;
int error = 0;
struct timeval start;
struct timeval stop;
struct bio *bio;
int err2;
unsigned nr_pages;
printk("Loading image data pages (%u pages) ... ", nr_to_read);
m = nr_to_read / 100;
if (!m)
m = 1;
nr_pages = 0;
bio = NULL;
do_gettimeofday(&start);
for ( ; ; ) {
error = snapshot_write_next(snapshot, PAGE_SIZE);
if (error <= 0)
break;
error = swap_read_page(handle, data_of(*snapshot), &bio);
if (error)
break;
if (snapshot->sync_read)
error = wait_on_bio_chain(&bio);
if (error)
break;
if (!(nr_pages % m))
printk("\b\b\b\b%3d%%", nr_pages / m);
nr_pages++;
}
err2 = wait_on_bio_chain(&bio);
do_gettimeofday(&stop);
if (!error)
error = err2;
if (!error) {
printk("\b\b\b\bdone\n");
[PATCH] swsusp: Improve handling of highmem Currently swsusp saves the contents of highmem pages by copying them to the normal zone which is quite inefficient (eg. it requires two normal pages to be used for saving one highmem page). This may be improved by using highmem for saving the contents of saveable highmem pages. Namely, during the suspend phase of the suspend-resume cycle we try to allocate as many free highmem pages as there are saveable highmem pages. If there are not enough highmem image pages to store the contents of all of the saveable highmem pages, some of them will be stored in the "normal" memory. Next, we allocate as many free "normal" pages as needed to store the (remaining) image data. We use a memory bitmap to mark the allocated free pages (ie. highmem as well as "normal" image pages). Now, we use another memory bitmap to mark all of the saveable pages (highmem as well as "normal") and the contents of the saveable pages are copied into the image pages. Then, the second bitmap is used to save the pfns corresponding to the saveable pages and the first one is used to save their data. During the resume phase the pfns of the pages that were saveable during the suspend are loaded from the image and used to mark the "unsafe" page frames. Next, we try to allocate as many free highmem page frames as to load all of the image data that had been in the highmem before the suspend and we allocate so many free "normal" page frames that the total number of allocated free pages (highmem and "normal") is equal to the size of the image. While doing this we have to make sure that there will be some extra free "normal" and "safe" page frames for two lists of PBEs constructed later. Now, the image data are loaded, if possible, into their "original" page frames. The image data that cannot be written into their "original" page frames are loaded into "safe" page frames and their "original" kernel virtual addresses, as well as the addresses of the "safe" pages containing their copies, are stored in one of two lists of PBEs. One list of PBEs is for the copies of "normal" suspend pages (ie. "normal" pages that were saveable during the suspend) and it is used in the same way as previously (ie. by the architecture-dependent parts of swsusp). The other list of PBEs is for the copies of highmem suspend pages. The pages in this list are restored (in a reversible way) right before the arch-dependent code is called. Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl> Cc: Pavel Machek <pavel@ucw.cz> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-12-07 11:34:18 +07:00
snapshot_write_finalize(snapshot);
if (!snapshot_image_loaded(snapshot))
error = -ENODATA;
}
swsusp_show_speed(&start, &stop, nr_to_read, "Read");
return error;
}
int swsusp_read(void)
{
int error;
struct swap_map_handle handle;
struct snapshot_handle snapshot;
struct swsusp_info *header;
if (IS_ERR(resume_bdev)) {
pr_debug("swsusp: block device not initialised\n");
return PTR_ERR(resume_bdev);
}
memset(&snapshot, 0, sizeof(struct snapshot_handle));
error = snapshot_write_next(&snapshot, PAGE_SIZE);
if (error < PAGE_SIZE)
return error < 0 ? error : -EFAULT;
header = (struct swsusp_info *)data_of(snapshot);
error = get_swap_reader(&handle, swsusp_header.image);
if (!error)
error = swap_read_page(&handle, header, NULL);
if (!error)
error = load_image(&handle, &snapshot, header->pages - 1);
release_swap_reader(&handle);
blkdev_put(resume_bdev);
if (!error)
pr_debug("swsusp: Reading resume file was successful\n");
else
pr_debug("swsusp: Error %d resuming\n", error);
return error;
}
/**
* swsusp_check - Check for swsusp signature in the resume device
*/
int swsusp_check(void)
{
int error;
resume_bdev = open_by_devnum(swsusp_resume_device, FMODE_READ);
if (!IS_ERR(resume_bdev)) {
set_blocksize(resume_bdev, PAGE_SIZE);
memset(&swsusp_header, 0, sizeof(swsusp_header));
error = bio_read_page(swsusp_resume_block,
&swsusp_header, NULL);
if (error)
return error;
if (!memcmp(SWSUSP_SIG, swsusp_header.sig, 10)) {
memcpy(swsusp_header.sig, swsusp_header.orig_sig, 10);
/* Reset swap signature now */
error = bio_write_page(swsusp_resume_block,
&swsusp_header, NULL);
} else {
return -EINVAL;
}
if (error)
blkdev_put(resume_bdev);
else
pr_debug("swsusp: Signature found, resuming\n");
} else {
error = PTR_ERR(resume_bdev);
}
if (error)
pr_debug("swsusp: Error %d check for resume file\n", error);
return error;
}
/**
* swsusp_close - close swap device.
*/
void swsusp_close(void)
{
if (IS_ERR(resume_bdev)) {
pr_debug("swsusp: block device not initialised\n");
return;
}
blkdev_put(resume_bdev);
}